{"id":"W2159136633","doi":"10.5555/2627435.2750354","title":"Efficient learning and planning with compressed predictive states","year":2014,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Observable; A priori and a posteriori; Dimensionality reduction; Machine learning; Curse of dimensionality","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001026199,0.0009278636,0.001028586,0.000536372,0.0003746466,0.000948375,0.00135248,0.001104333,0.002405137],"category_scores_gemma":[0.006623545,0.0007307275,0.0006333207,0.0006720937,0.001503629,0.002236263,0.001775384,0.002209593,0.0002967267],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001113137,"about_ca_system_score_gemma":0.001662961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006722506,"about_ca_topic_score_gemma":0.006948614,"domain_scores_codex":[0.9993501,0.000222108,0.00003564175,0.0001356369,0.0001873099,0.00006918975],"domain_scores_gemma":[0.9969933,0.002185991,0.0002607538,0.0002964257,0.0001880986,0.00007538916],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005929076,0.00002287417,0.0001813667,0.00004882509,0.000013479,0.00004899188,0.00006455972,0.945515,0.0006830539,0.03112112,0.0007127859,0.02152873],"study_design_scores_gemma":[0.000005063904,0.00000817096,0.00001863986,0.000004436293,0.000001732015,0.000005608599,0.000004447311,0.9857195,0.0002363723,0.01381871,0.0001747097,0.00000266212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009767411,0.0001413065,0.9876452,0.0002537833,0.00002161835,0.00003966036,0.0001056526,0.0004894075,0.001536029],"genre_scores_gemma":[0.6970861,0.0003666247,0.2987481,0.0002175484,0.00007314551,0.0003132034,0.0005853173,0.0001768639,0.002433136],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006722506,"threshold_uncertainty_score":0.01336676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0249183959460578,"score_gpt":0.331304983517485,"score_spread":0.3063865875714272,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}